News for hackers. Stuff that matters.
Re:Ask HN: Pure mathematical route to intelligence? by mindcrime on Friday August 17, 2018 @11:57AM (#17783713)
The closest thing I can think of would be Algorithmic Information Theory[1]. Marcus Hutter has done some work with that vis-a-vis Artificial Intelligence[2][3][4]. And while it's not quite the same thing, you might find Pei Wang's NARS[5] approach of interest.

[1]: https://en.wikipedia.org/wiki/Algorithmic_information_theory

[2]: http://www.hutter1.net/ait.htm

[3]: http://www.hutter1.net/ai/uaibook.htm

[4]: https://en.wikipedia.org/wiki/AIXI

[5]: https://cis.temple.edu/~pwang/papers.html

Re:Ask HN: Pure mathematical route to intelligence? by antidesitter on Friday August 17, 2018 @07:13PM (#17786023)
I was going to say the same thing. You might also be interested in logical induction:

https://golem.ph.utexas.edu/category/2016/09/logical_uncerta...

https://intelligence.org/2016/09/12/new-paper-logical-induct...

Re:Ask HN: Pure mathematical route to intelligence? by friendoamano on Friday August 17, 2018 @12:19PM (#17783895)
Thanks for the links especially the Marcus Hutter links